Triple
T20051388
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garioch |
E499207
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Oldmeldrum |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Oldmeldrum | Statement: [Garioch, hasSettlement, Oldmeldrum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Oldmeldrum Context triple: [Garioch, hasSettlement, Oldmeldrum]
-
A.
Oldmeldrum
chosen
Oldmeldrum is a small historic town in Aberdeenshire, Scotland, known for its whisky distillery and agricultural heritage.
-
B.
Barholm
Barholm is a small village and civil parish in Lincolnshire, England, known for its rural character and historic parish church.
-
C.
Sallands
Sallands is a Dutch Low Saxon dialect spoken in the Salland region of the province of Overijssel in the Netherlands.
-
D.
Molendinar
Molendinar is a suburb in the City of Gold Coast, Queensland, Australia, known for its mix of residential areas and light industrial and commercial precincts.
-
E.
Dunkeld
Dunkeld is a historic town in Perth and Kinross, Scotland, known for its picturesque setting on the River Tay and its medieval cathedral.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6632ee4d48190b9de3a1efa064492 |
completed | April 20, 2026, 5:32 p.m. |
Created at: April 11, 2026, 3:38 p.m.